US 11,928,112 B2
Systems and methods for intelligent responses to queries based on trained processes
Milos Dunjic, Oakville (CA); Martin Albert Lozon, London (CA); David Samuel Tax, Toronto (CA); Arthur Carroll Chow, Markham (CA); Peter Glen Nairn, Cobourg (CA); Edward James Hood, Toronto (CA); John Jong-Suk Lee, Toronto (CA); and Arun Victor Jagga, Toronto (CA)
Assigned to The Toronto-Dominion Bank, Toronto (CA)
Filed by THE TORONTO-DOMINION BANK, Toronto (CA)
Filed on Apr. 23, 2021, as Appl. No. 17/239,233.
Application 17/239,233 is a continuation of application No. 16/150,483, filed on Oct. 3, 2018, granted, now 11,017,028.
Prior Publication US 2021/0240778 A1, Aug. 5, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/2455 (2019.01); G06F 9/54 (2006.01); G06N 20/00 (2019.01); G10L 15/06 (2013.01)
CPC G06F 16/2455 (2019.01) [G06F 9/54 (2013.01); G06N 20/00 (2019.01); G10L 15/063 (2013.01)] 34 Claims
OG exemplary drawing
 
1. A computing device comprising a processor and a storage device coupled to the processor, the storage device storing instructions to configure operation of the computing device when executed by the processor, wherein the computing device is configured to:
provide an execution plan generation component for generating a plan to respond to a request, the plan comprising one or more selected Application Programming Interfaces (APIs) from a plurality of APIs, the plan generated using a trained process trained to select a particular API of the plurality of APIs for the plan responsive to the capabilities of the particular API to answer at least a portion of the request and the selected APIs together prepare a response optimized according to a context of the request; and
in response to an update to the plurality of APIs:
retrain the trained process to accommodate the update to the plurality of APIs;
wherein the request comprises query data defining a query and context data defining contextual factors for responding to the query, the context data comprising either or both of:
requesting device data providing technical capabilities of a requesting device to process the response; or
network communication data providing technical capabilities of a network in communication with the requesting device for communicating the response; and
wherein two or more APIs of the plurality of APIs are capable to each answer the at least the portion of the request and the context data is used to optimize a selection between the two or more APIs according to the technical capabilities in the context data.